- Implemented the WiFi DensePose model in PyTorch, including CSI phase processing, modality translation, and DensePose prediction heads. - Added a comprehensive training utility for the model, including loss functions and training steps. - Created a CSV file to document hardware specifications, architecture details, training parameters, performance metrics, and advantages of the model.
4.4 KiB
4.4 KiB
| 1 | Category | Metric | Value | Unit | Description |
|---|---|---|---|---|---|
| 2 | Hardware | WiFi_Transmitters | 3 | count | Number of WiFi transmitter antennas |
| 3 | Hardware | WiFi_Receivers | 3 | count | Number of WiFi receiver antennas |
| 4 | Hardware | Frequency_Range | 2.4GHz ± 20MHz | frequency | Operating frequency range |
| 5 | Hardware | Subcarriers | 30 | count | Number of subcarrier frequencies |
| 6 | Hardware | Sampling_Rate | 100 | Hz | CSI data sampling rate |
| 7 | Hardware | Total_Cost | 30 | USD | Hardware cost using TP-Link AC1750 routers |
| 8 | Architecture | Input_Amplitude_Shape | 150x3x3 | tensor | CSI amplitude input dimensions |
| 9 | Architecture | Input_Phase_Shape | 150x3x3 | tensor | CSI phase input dimensions |
| 10 | Architecture | Output_Feature_Shape | 3x720x1280 | tensor | Spatial feature map dimensions |
| 11 | Architecture | Body_Parts | 24 | count | Number of body parts detected |
| 12 | Architecture | Keypoints | 17 | count | Number of keypoints tracked (COCO format) |
| 13 | Training | Learning_Rate | 0.001 | rate | Initial learning rate |
| 14 | Training | Batch_Size | 16 | count | Training batch size |
| 15 | Training | Total_Iterations | 145000 | count | Total training iterations |
| 16 | Training | Lambda_DensePose | 0.6 | weight | DensePose loss weight |
| 17 | Training | Lambda_Keypoint | 0.3 | weight | Keypoint loss weight |
| 18 | Training | Lambda_Transfer | 0.1 | weight | Transfer learning loss weight |
| 19 | Performance | WiFi_Same_Layout_AP | 43.5 | AP | AP for WiFi_Same_Layout |
| 20 | Performance | WiFi_Same_Layout_AP@50 | 87.2 | AP | AP@50 for WiFi_Same_Layout |
| 21 | Performance | WiFi_Same_Layout_AP@75 | 44.6 | AP | AP@75 for WiFi_Same_Layout |
| 22 | Performance | WiFi_Same_Layout_AP-m | 38.1 | AP | AP-m for WiFi_Same_Layout |
| 23 | Performance | WiFi_Same_Layout_AP-l | 46.4 | AP | AP-l for WiFi_Same_Layout |
| 24 | Performance | WiFi_Same_Layout_dpAP_GPS | 45.3 | AP | dpAP_GPS for WiFi_Same_Layout |
| 25 | Performance | WiFi_Same_Layout_dpAP_GPS@50 | 79.3 | AP | dpAP_GPS@50 for WiFi_Same_Layout |
| 26 | Performance | WiFi_Same_Layout_dpAP_GPS@75 | 47.7 | AP | dpAP_GPS@75 for WiFi_Same_Layout |
| 27 | Performance | WiFi_Same_Layout_dpAP_GPSm | 43.2 | AP | dpAP_GPSm for WiFi_Same_Layout |
| 28 | Performance | WiFi_Same_Layout_dpAP_GPSm@50 | 77.4 | AP | dpAP_GPSm@50 for WiFi_Same_Layout |
| 29 | Performance | WiFi_Same_Layout_dpAP_GPSm@75 | 45.5 | AP | dpAP_GPSm@75 for WiFi_Same_Layout |
| 30 | Performance | Image_Same_Layout_AP | 84.7 | AP | AP for Image_Same_Layout |
| 31 | Performance | Image_Same_Layout_AP@50 | 94.4 | AP | AP@50 for Image_Same_Layout |
| 32 | Performance | Image_Same_Layout_AP@75 | 77.1 | AP | AP@75 for Image_Same_Layout |
| 33 | Performance | Image_Same_Layout_AP-m | 70.3 | AP | AP-m for Image_Same_Layout |
| 34 | Performance | Image_Same_Layout_AP-l | 83.8 | AP | AP-l for Image_Same_Layout |
| 35 | Performance | Image_Same_Layout_dpAP_GPS | 81.8 | AP | dpAP_GPS for Image_Same_Layout |
| 36 | Performance | Image_Same_Layout_dpAP_GPS@50 | 93.7 | AP | dpAP_GPS@50 for Image_Same_Layout |
| 37 | Performance | Image_Same_Layout_dpAP_GPS@75 | 86.2 | AP | dpAP_GPS@75 for Image_Same_Layout |
| 38 | Performance | Image_Same_Layout_dpAP_GPSm | 84.0 | AP | dpAP_GPSm for Image_Same_Layout |
| 39 | Performance | Image_Same_Layout_dpAP_GPSm@50 | 94.9 | AP | dpAP_GPSm@50 for Image_Same_Layout |
| 40 | Performance | Image_Same_Layout_dpAP_GPSm@75 | 86.8 | AP | dpAP_GPSm@75 for Image_Same_Layout |
| 41 | Performance | WiFi_Different_Layout_AP | 27.3 | AP | AP for WiFi_Different_Layout |
| 42 | Performance | WiFi_Different_Layout_AP@50 | 51.8 | AP | AP@50 for WiFi_Different_Layout |
| 43 | Performance | WiFi_Different_Layout_AP@75 | 24.2 | AP | AP@75 for WiFi_Different_Layout |
| 44 | Performance | WiFi_Different_Layout_AP-m | 22.1 | AP | AP-m for WiFi_Different_Layout |
| 45 | Performance | WiFi_Different_Layout_AP-l | 28.6 | AP | AP-l for WiFi_Different_Layout |
| 46 | Performance | WiFi_Different_Layout_dpAP_GPS | 25.4 | AP | dpAP_GPS for WiFi_Different_Layout |
| 47 | Performance | WiFi_Different_Layout_dpAP_GPS@50 | 50.2 | AP | dpAP_GPS@50 for WiFi_Different_Layout |
| 48 | Performance | WiFi_Different_Layout_dpAP_GPS@75 | 24.7 | AP | dpAP_GPS@75 for WiFi_Different_Layout |
| 49 | Performance | WiFi_Different_Layout_dpAP_GPSm | 23.2 | AP | dpAP_GPSm for WiFi_Different_Layout |
| 50 | Performance | WiFi_Different_Layout_dpAP_GPSm@50 | 47.4 | AP | dpAP_GPSm@50 for WiFi_Different_Layout |
| 51 | Performance | WiFi_Different_Layout_dpAP_GPSm@75 | 26.5 | AP | dpAP_GPSm@75 for WiFi_Different_Layout |
| 52 | Ablation | Amplitude_Only_AP | 39.5 | AP | Performance with amplitude only |
| 53 | Ablation | Plus_Phase_AP | 40.3 | AP | Performance adding phase information |
| 54 | Ablation | Plus_Keypoints_AP | 42.9 | AP | Performance adding keypoint supervision |
| 55 | Ablation | Final_Model_AP | 43.5 | AP | Performance with transfer learning |
| 56 | Advantages | Through_Walls | Yes | boolean | Can detect through walls and obstacles |
| 57 | Advantages | Privacy_Preserving | Yes | boolean | No visual recording required |
| 58 | Advantages | Lighting_Independent | Yes | boolean | Works in complete darkness |
| 59 | Advantages | Low_Cost | Yes | boolean | Uses standard WiFi equipment |
| 60 | Advantages | Real_Time | Yes | boolean | Multiple frames per second |
| 61 | Advantages | Multiple_People | Yes | boolean | Can track multiple people simultaneously |